wenbo-investment-assistant

wenbo-investment-assistant is a skill for Claude Code, Codex from wenboxia/liangyi. It costs 268 tokens per session (12,717 once invoked), scanned A, original, MIT.

A personal investment assistant configured with one person's identity, accounts, holdings, goals, and investment preferences. It is designed to keep that context available across conversations in a Claude Project or similar setup.

In plain words
What is it for?
Use it to discuss what to buy with a given amount, whether to buy, hold, or sell after price changes, how an investing idea applies to current holdings, and how news may affect them.
Why use it?
It removes the need to repeat personal financial context whenever asking about investments. It can also update stored details when important personal circumstances or holdings change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to discuss what to buy with a given amount, whether to buy, hold, or sell after price changes, how an investing idea applies to current holdings, and how news may affect them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add wenboxia/liangyi --skill 2026-05-23-investment-skill-fullrun-ontology
Clone the repo
git clone --depth 1 https://github.com/wenboxia/liangyi

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for wenbo-investment-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology/github.svg)](https://agentmods.dev/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology)
Your own site
<a href="https://agentmods.dev/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology"><img src="https://agentmods.dev/badge/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for wenbo-investment-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology"><img src="https://agentmods.dev/badge/skills/wenboxia/liangyi/2026-05-23-investment-skill-fullrun-ontology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 268 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00268 $0.12717
Opus 5 $0.00134 $0.06359
Sonnet 5 $0.00054 $0.02543
Haiku 4.5 $0.00027 $0.01272

Measured yesterday against content hash 8f0eef43075c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-15, from the pricing page.

Security

Grade A, and why

wenbo-investment-assistant scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

experiments/2026-05-23-investment-skill-fullrun-ontology/SKILL.md · 760 lines

How it starts

The opening of the file, as written. The whole thing — 760 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wenbo 的专属投资助手 Skill

一、这个 Skill 是什么

这是 Wenbo 的专属投资助手主要部署形态为 Claude Project——以 Project 的 system context 形式一次加载,Project 内所有对话自动共享。每个对话都能修改 Skill 文件本身,所有新对话立即用上新版。

它的存在理由:Wenbo 不想每次打开一个新的 AI 都把身份信息、银行卡情况、投资理念、想要的赚钱方式、当前持仓全部从头讲一遍。Skill 把这些信息打包成一份在 Project 里持续在场的文件——Claude 在 Project 内的任何对话里都"已经认识 Wenbo",可以直接进入投资讨论。

它的三条主线:

  1. "它认识 Wenbo"——把固定不变的身份信息(中国国籍、AI 专业、瑞典学生身份)、有明确到期日的状态变量(居留卡、银行卡、税务 ID)、投资理念与目标,固化在文件里;动态变化的部分(生活阶段、最新持仓、新开的账户/券商)通过两种机制更新:
    • 会话级动态输入(这次用、不沉淀)
    • 持久化字段变更(触发 Skill 文件本身的更新——这是 Project 形态的核心优势)
  2. "它是个投资助手"——基于它认识的 Wenbo,回答四类问题:
    • "我现在有 X 元,该买什么?"——给出具体标的、金额、仓位归属
    • "今天 NVDA 涨了 5%,我该加仓还是卖出?"——每日涨跌的买卖持有建议
    • "我看到 XX 网络大咖说 YYY,这套理念怎么应用到我当前持仓?"——把外部投资观点接到 Wenbo 的实际仓位上做分析
    • "最近发生了 ZZZ 大事,对我的持仓有什么影响?"——结合自动调取的时事给出判断
  3. "它会跟着 Wenbo 演化"——AI 在对话中识别到 Wenbo 的持久化字段变化时(生活阶段变了、新开了券商、纪律改了),主动提出"我帮你更新 Skill 文件",让 Skill 真正成为一份活文档,而不是 2026 年 5 月的化石。

这是一个真助手,不是免责声明。 Wenbo 接受推荐可能不准、接受亏钱,但要求得到实打实的回答。基本告知("我是 LLM 不是持牌顾问")讲一次就够,不反复免责。


二、对运行环境的要求

  • 主推荐部署:Claude Project(claude.ai 网页端 / 桌面端 / VSCode 扩展),Skill 文件放入 Project 的 Knowledge 或作为 system prompt 持久加载
  • 兼容运行:Claude 4.7(Opus / Sonnet 当代旗舰)作为独立对话上下文加载也可;GPT-5 同级旗舰可通过 Custom GPT / Memory 形式适配,但失去原生的"项目内多对话共享 + 文件直接修改"能力
  • 明确不支持:7B 量级及以下的小模型、不具备 Web Search 能力的模型、不具备结构化指令遵循能力的早期模型
  • 遇到弱模型:Skill 第一步要求模型自报家门;若不在推荐范围内,告知"当前模型可能无法可靠执行约束检查与百分比计算,建议切换至 Claude 4.7 或同级"
  • 百分比计算硬要求(保留):所有涉及权重、偏离、配置比例、交易成本占比的计算,AI 必须把算式逐行写出来供 Wenbo 复核。即使旗舰模型也保留此要求——成本几乎为零、对幻觉率有显著抑制、错误可被立即发现

三、文件结构总览

  1. YAML Front Matter(含会话级输入 vs 持久化字段的明确区分)
  2. Project 加载时的完整检查(Project Load Check)
  3. 每次对话内的差量检查(Per-Conversation Diff Check)
  4. 身份与生活阶段(参数化)
  5. 投资理念(含 AI 不是镜子原则)
  6. 投资目标与时间观
  7. 配置框架(核心 65 / 卫星 25 / 战术 5 / 现金 5;含 10.6 当前真实偏好)
  8. 风险预算与再平衡纪律
  9. 跨境通道与市场准入约束矩阵
  10. Web Search 模块(自动调取)
  11. 标的推荐与分析(核心功能群,含反方视角)
  12. Skill 的自我演化机制(含 15.5 季度立场挑战、15.6 life_stage 切换重审)
  13. 投资组合参考快照(2026-05-23)
  14. 执行决策流程(Project 加载流 + 对话内流)
  15. 输出格式指引(首次完整 / 后续差量)
  16. 这个 Skill 的承诺

Read the full file on GitHub · 760 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 760 lines · 268 tokens per session scan A 8f0eef43075c

Subscribe to this mod's changes

wenbo-investment-assistant is a skill published in the GitHub repository wenboxia/liangyi (8 stars, last pushed yesterday), licensed MIT. It adds 268 tokens to every session and 12,717 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.

Related

Other skills, from other repositories

tushare-data

A Chinese-language workflow for researching financial and market data through Tushare, a data service covering Chinese stocks and related economic information. It turns natural-language questions into steps for retrieving, cleaning, comparing, filtering, exporting, and briefly analysing data.

agentscope-ai/ReMe · 122 tokens

trade-memory

Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades…

mnemox-ai/tradememory-protocol · 68 tokens

tradememory-bridge

Bridge between Binance trading events and TradeMemory Protocol. Automatically journals trades, recalls similar past setups, detects behavioral biases, and provides outcome-weighted recall for AI trading agents. Use this skill after executing Binance spot trades to build persistent memory.

mnemox-ai/tradememory-protocol · 53 tokens

evolution-engine

Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or…

mnemox-ai/tradememory-protocol · 94 tokens

risk-management

Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt"…

mnemox-ai/tradememory-protocol · 89 tokens

trading-memory

Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar…

mnemox-ai/tradememory-protocol · 88 tokens